xop: initial implementation

XOP was an AMD ISA extension which Intel never adopted.  It is present
on heavy-equipment CPUs (bulldozer, piledriver, etc.), but no longer
supported on Zen.  It never really attained widespread use, but this
could still be useful.

Huge thanks to Jan Ringoš (@tringi) for testing this during
development; I don't have access to any hardware that supports XOP
so Jan's involvement was absolutely critical.

This is just the portable version; we still need to go through and add
accelerated implementations.

Fixes #678

simde-arch.h

@@ -254,6 +254,9 @@
 #  if defined(__SSE4_2__)
 #    define SIMDE_ARCH_X86_SSE4_2 1
 #  endif
+#  if defined(__XOP__)
+#    define SIMDE_ARCH_X86_XOP 1
+#  endif
 #  if defined(__AVX__)
 #    define SIMDE_ARCH_X86_AVX 1
 #    if !defined(SIMDE_ARCH_X86_SSE3)

simde-common.h

@@ -806,6 +806,7 @@ HEDLEY_DIAGNOSTIC_POP
 #      if !HEDLEY_GCC_VERSION_CHECK(11,0,0)
 #        define SIMDE_BUG_GCC_95483
 #      endif
+#      define SIMDE_BUG_GCC_98521
 #    endif
 #    if !HEDLEY_GCC_VERSION_CHECK(9,4,0) && defined(SIMDE_ARCH_AARCH64)
 #      define SIMDE_BUG_GCC_94488
@@ -844,6 +845,7 @@ HEDLEY_DIAGNOSTIC_POP
 #      if HEDLEY_HAS_WARNING("-Wvector-conversion") && SIMDE_DETECT_CLANG_VERSION_NOT(11,0,0)
 #        define SIMDE_BUG_CLANG_44589
 #      endif
+#      define SIMDE_BUG_CLANG_48673
 #    endif
 #    define SIMDE_BUG_CLANG_45959
 #  elif defined(HEDLEY_MSVC_VERSION)

simde-features.h

@@ -133,6 +133,15 @@
   #define SIMDE_X86_SSE4_2_NATIVE
 #endif
 
+#if !defined(SIMDE_X86_XOP_NATIVE) && !defined(SIMDE_X86_XOP_NO_NATIVE) && !defined(SIMDE_NO_NATIVE)
+  #if defined(SIMDE_ARCH_X86_XOP)
+    #define SIMDE_X86_XOP_NATIVE
+  #endif
+#endif
+#if defined(SIMDE_X86_XOP_NATIVE) && !defined(SIMDE_X86_SSE4_2_NATIVE)
+  #define SIMDE_X86_SSE4_2_NATIVE
+#endif
+
 #if !defined(SIMDE_X86_SSE4_2_NATIVE) && !defined(SIMDE_X86_SSE4_2_NO_NATIVE) && !defined(SIMDE_NO_NATIVE)
   #if defined(SIMDE_ARCH_X86_SSE4_2)
     #define SIMDE_X86_SSE4_2_NATIVE
@@ -238,6 +247,14 @@
   #include <mmintrin.h>
 #endif
 
+#if defined(SIMDE_X86_XOP_NATIVE)
+  #if defined(_MSC_VER)
+    #include <intrin.h>
+  #else
+    #include <x86intrin.h>
+  #endif
+#endif
+
 #if defined(HEDLEY_MSVC_VERSION)
   #pragma warning(pop)
 #endif